forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Dockerfile
159 lines (124 loc) · 5.52 KB
/
Dockerfile
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
# The vLLM Dockerfile is used to construct vLLM image that can be directly used
# to run the OpenAI compatible server.
# Please update any changes made here to
# docs/source/dev/dockerfile/dockerfile.rst and
# docs/source/assets/dev/dockerfile-stages-dependency.png
#################### BASE BUILD IMAGE ####################
# prepare basic build environment
FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 AS dev
RUN apt-get update -y \
&& apt-get install -y python3-pip git
# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
# this won't be needed for future versions of this docker image
# or future versions of triton.
RUN ldconfig /usr/local/cuda-12.1/compat/
WORKDIR /workspace
# install build and runtime dependencies
COPY requirements-common.txt requirements-common.txt
COPY requirements-cuda.txt requirements-cuda.txt
RUN --mount=type=cache,target=/root/.cache/pip \
pip install -r requirements-cuda.txt
# install development dependencies
COPY requirements-dev.txt requirements-dev.txt
RUN --mount=type=cache,target=/root/.cache/pip \
pip install -r requirements-dev.txt
# cuda arch list used by torch
# can be useful for both `dev` and `test`
# explicitly set the list to avoid issues with torch 2.2
# see https://github.com/pytorch/pytorch/pull/123243
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.6 8.9 9.0+PTX'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
#################### BASE BUILD IMAGE ####################
#################### WHEEL BUILD IMAGE ####################
FROM dev AS build
# install build dependencies
COPY requirements-build.txt requirements-build.txt
RUN --mount=type=cache,target=/root/.cache/pip \
pip install -r requirements-build.txt
# install compiler cache to speed up compilation leveraging local or remote caching
RUN apt-get update -y && apt-get install -y ccache
# files and directories related to build wheels
COPY csrc csrc
COPY setup.py setup.py
COPY cmake cmake
COPY CMakeLists.txt CMakeLists.txt
COPY requirements-common.txt requirements-common.txt
COPY requirements-cuda.txt requirements-cuda.txt
COPY pyproject.toml pyproject.toml
COPY vllm vllm
# max jobs used by Ninja to build extensions
ARG max_jobs=2
ENV MAX_JOBS=${max_jobs}
# number of threads used by nvcc
ARG nvcc_threads=8
ENV NVCC_THREADS=$nvcc_threads
# make sure punica kernels are built (for LoRA)
ENV VLLM_INSTALL_PUNICA_KERNELS=1
ENV CCACHE_DIR=/root/.cache/ccache
RUN --mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/root/.cache/pip \
python3 setup.py bdist_wheel --dist-dir=dist
# the `vllm_nccl` package must be installed from source distribution
# pip is too smart to store a wheel in the cache, and other CI jobs
# will directly use the wheel from the cache, which is not what we want.
# we need to remove it manually
RUN --mount=type=cache,target=/root/.cache/pip \
pip cache remove vllm_nccl*
#################### EXTENSION Build IMAGE ####################
#################### FLASH_ATTENTION Build IMAGE ####################
FROM dev as flash-attn-builder
# max jobs used for build
ARG max_jobs=2
ENV MAX_JOBS=${max_jobs}
# flash attention version
ARG flash_attn_version=v2.5.8
ENV FLASH_ATTN_VERSION=${flash_attn_version}
WORKDIR /usr/src/flash-attention-v2
# Download the wheel or build it if a pre-compiled release doesn't exist
RUN pip --verbose wheel flash-attn==${FLASH_ATTN_VERSION} \
--no-build-isolation --no-deps --no-cache-dir
#################### FLASH_ATTENTION Build IMAGE ####################
#################### vLLM installation IMAGE ####################
# image with vLLM installed
FROM nvidia/cuda:12.1.0-base-ubuntu22.04 AS vllm-base
WORKDIR /vllm-workspace
RUN apt-get update -y \
&& apt-get install -y python3-pip git vim
# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
# this won't be needed for future versions of this docker image
# or future versions of triton.
RUN ldconfig /usr/local/cuda-12.1/compat/
# install vllm wheel first, so that torch etc will be installed
RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
--mount=type=cache,target=/root/.cache/pip \
pip install dist/*.whl --verbose
RUN --mount=type=bind,from=flash-attn-builder,src=/usr/src/flash-attention-v2,target=/usr/src/flash-attention-v2 \
--mount=type=cache,target=/root/.cache/pip \
pip install /usr/src/flash-attention-v2/*.whl --no-cache-dir
#################### vLLM installation IMAGE ####################
#################### TEST IMAGE ####################
# image to run unit testing suite
# note that this uses vllm installed by `pip`
FROM vllm-base AS test
ADD . /vllm-workspace/
# install development dependencies (for testing)
RUN --mount=type=cache,target=/root/.cache/pip \
pip install -r requirements-dev.txt
# doc requires source code
# we hide them inside `test_docs/` , so that this source code
# will not be imported by other tests
RUN mkdir test_docs
RUN mv docs test_docs/
RUN mv vllm test_docs/
#################### TEST IMAGE ####################
#################### OPENAI API SERVER ####################
# openai api server alternative
FROM vllm-base AS vllm-openai
# install additional dependencies for openai api server
RUN --mount=type=cache,target=/root/.cache/pip \
pip install accelerate hf_transfer modelscope
ENV VLLM_USAGE_SOURCE production-docker-image
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
#################### OPENAI API SERVER ####################